{"version":"1.1.0","schema":"https://www.oneagentaday.com/api/schema.json","agent":{"title":"Interview Decoder","slug":"interview-decoder","date":"2026-10-19","issue":45,"category":"research","categoryLabel":"Research","tags":["user-research","interviews","product","startups"],"difficulty":"medium","runtimes":["ChatGPT","Claude","Gemini"],"excerpt":"Paste notes from a few customer interviews. Get what actually came up again and again, counted (\"3 of 6\") and backed by real quotes, plus what to ask next.","problem":"You did six customer calls. You have pages of notes, a vague feeling that people liked it, and no idea which complaints came up once and which came up every time.","videoUrl":null,"url":"https://www.oneagentaday.com/agents/interview-decoder","apiUrl":"https://www.oneagentaday.com/api/agents/interview-decoder.json","promptUrl":"https://www.oneagentaday.com/agents/interview-decoder/prompt.txt","configUrl":null,"configFilename":null,"license":"CC-BY-4.0","howItWorks":"After a round of customer interviews, the loudest memory wins. The person who complained the most, or the last call you did, starts to feel like \"what users want.\" Proper synthesis means going back through every note, pulling quotes, and counting. It takes hours, so most people skip it.\n\nThis agent does that grunt work. It reads every interview against the question you were trying to answer, pulls exact quotes, groups the ones that say the same thing, and counts how many different people said it.\n\n## What to paste\n\nOne line on what you wanted to learn. Then each interview, labeled P1, P2, and so on, with who the person is. Rough notes are fine. If you have transcripts, paste those. It will only quote what's actually there.\n\n## What you get back\n\nPatterns ranked by how many people mentioned them, not by how strongly one person felt. Each pattern has a count (\"3 of 6\"), two or three exact quotes with who said them, and what it might mean for your question.\n\nThen a short list of one-off opinions it deliberately kept out of the patterns, a list of surprises (things nobody asked about but came up anyway), and follow-up questions for the next round. It won't invent a quote or round 2 people up to \"most users.\"","steps":[{"name":"Gather every interview","text":"Paste notes or transcripts for each call, labeled P1, P2, and so on, with a few words on who the person is. Rough notes work. Transcripts work better."},{"name":"State the question","text":"Write one line at the top saying what you were trying to learn. The agent sorts everything against that question instead of summarizing each call."},{"name":"Run the prompt","text":"New chat in Claude, ChatGPT, or Gemini. Paste the prompt, then the notes. For long transcripts, use a model with a big context window or run it in two halves and paste both outputs back."},{"name":"Decide what's next","text":"Read the patterns with their counts. Anything 1 in 6 is a hunch, not a finding. Use the follow-up questions in your next round of calls."}],"demo":[{"second":0,"label":"The notes","detail":"Six trial-user calls for an invoicing app. Goal: find out why trials don't convert."},{"second":8,"label":"Quotes pulled","detail":"Exact lines lifted from every call, each tagged with who said it."},{"second":16,"label":"Patterns","detail":"Exports are broken (2 of 6). Nobody found in-app sending (2 of 6). Dashboard is loved (1 of 6, but daily use)."},{"second":24,"label":"Flagged","detail":"Dark mode: one person, said loudly. Logged, not a priority. Plus three questions for the next round."}],"sampleInput":"Interviews for our invoicing tool, Oct 2026. Goal: why do trial users not convert?\n\nP1 (freelance designer): Signed up for the templates. Gave up on exports,\n\"the PDF took like a minute and looked off on mobile\". Pays for Bonsai now.\n\nP2 (agency owner, 8 people): \"Honestly I just screenshot the invoice and\nsend that.\" Didn't know you could send from the app. Wants team seats.\n\nP3 (bookkeeper): Loves the dashboard. Uses it daily. Pricing feels fine.\n\nP4 (dev contractor): Export again. \"CSV broke my accounting import, dates\nwere in US format\". Almost churned.\n\nP5 (photographer): Wants dark mode, said it three times. Otherwise happy.\n\nP6 (consultant): Didn't realize invoices could be sent from the app either.\nWas copying the link into Gmail.\n","prompt":"You synthesize user interviews. You are a careful researcher: you separate what people said from what you think it means, and you never inflate a finding.\n\nINPUT\n- One research question (what the interviews were meant to learn).\n- Notes or transcripts from several interviews, labeled P1, P2, and so on, with a short description of each person.\n\nHOW TO WORK\n1. Read every interview. Pull short exact quotes or note lines that relate to the research question. Tag each with its participant label.\n2. Group quotes that express the same underlying point. Name each group as a plain statement of what users experience (\"Exports break their accounting import\"), not a solution.\n3. Count distinct participants per group, not mentions. One person saying it five times is still 1.\n4. Rank groups by participant count. A group needs at least 2 participants to be a pattern.\n5. Keep single-participant points in a separate list, even if they were said with feeling.\n6. Note anything surprising that came up without being asked.\n7. Write follow-up questions that would confirm or kill the top patterns.\n\nRULES\n- Only quote what is in the notes. If notes are paraphrased, say \"(from notes)\" instead of using quotation marks.\n- Always write counts as \"X of N\", where N is the number of interviews.\n- Do not use words like \"most\" or \"many\" unless more than half of participants said it.\n- Do not suggest features or fixes. The user decides that.\n- If there are fewer than 3 interviews, say the sample is too small for patterns and give quotes only.\n\nOUTPUT\n## Answer in one paragraph\nWhat the interviews say about the research question, with counts.\n\n## Patterns\nFor each, ranked: a heading with the statement and \"X of N\", then 2 or 3 quotes with participant labels, then one line on what it suggests for the research question.\n\n## One-off points\nBullets with the participant label. Not patterns yet.\n\n## Surprises\nBullets, or \"None\".\n\n## Ask next time\n3 to 5 follow-up questions, each tied to a pattern.","config":null}}